A computer-implemented method includes storing, by a computing device, a plurality of dialogs between user devices and an automated support application hosted by the computing device; determining, by the computing device, transitive relationships between the plurality of dialogs; and updating, by the computing device, a question mapping based on the determining the transitive relationships; and applying, the computing device, the updated question mapping to a subsequent support dialog.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A computer-implemented method comprising: storing, by a computing device, a plurality of dialogues between user devices and an automated support application hosted by the computing device; determining, by the computing device, transitive relationships between the plurality of dialogues; and updating, by the computing device, a question mapping based on the determining the transitive relationships; and applying, by the computing device, the updated question mapping to a subsequent support dialogue, wherein the storing the plurality of dialogues includes storing respective dialogue graphs associated with each of the plurality of dialogues, and the determining the transitive relationships includes matching a subset of the plurality of dialogues based on respective dialogue graphs of each of the subset of the plurality of dialogues.
2. The method of claim 1 , wherein the updating the question mapping reduces a number of questions included in the question mapping.
3. The method of claim 1 , wherein storing a dialogue graph of the respective dialog graphs comprises generating the dialogue graph, wherein the generating the dialogue graph comprises generating nodes representing responses by each of the user device and the automated support application and a path between the responses.
4. The method of claim 3 , wherein the generating the dialogue graph further comprises storing indications of one or more classifications determined at each node in the graph.
5. The method of claim 3 , wherein the nodes in the dialogue graph represent follow-up questions presented by the automated support application and responses to the follow-up questions.
6. The method of claim 1 , wherein the determining the transitive relationships further comprises determining a shortest path between a node representing an initial utterance and a node representing a resolution.
7. The method of claim 1 , further comprising scoring user responses within the plurality of dialogues, wherein the updating is further based on the scoring the user responses.
8. The method of claim 1 , wherein a service provider at least one of creates, maintains, deploys and supports the computing device.
9. The method of claim 1 , wherein the storing the plurality of dialogues, the determining the transitive relationships, the updating the question mapping, and the applying the updated question map are provided by a service provider on a subscription, advertising, and/or fee basis.
10. The method of claim 1 , wherein the computing device includes software provided as a service in a cloud environment.
11. The method of claim 1 , further comprising deploying a system for streamlining user support dialogues, comprising providing a computer infrastructure operable to perform the storing the plurality of dialogues, the determining the transitive relationships, the updating the question mapping, and the applying the updated question map.
12. A computer program product for streamlining support dialogues, the computer program product comprising a computer readable non-transitory storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to: receive, via an automated support application hosted by the computing device, an initial user input from a user via a user device; provide one or more follow-up questions based on receiving the initial user input and a question mapping; receive one or more follow-up responses to the one or more follow-up questions; store a dialogue, wherein the dialogue includes the initial user input, the one or more follow-up questions, and the one or more follow-up responses; determine a transitive relationship between the stored dialogue and one more previously stored dialogues; update the question mapping based on the determining the transitive relationships; and apply the updated question mapping to a subsequent support dialogue, wherein the determining the transitive relationships includes comparing dialogue graphs associated with the stored dialogue and the one more previously stored dialogues.
13. The computer program product of claim 12 , wherein the program instructions further cause the computing device to apply natural language processing to automatically determine one or more classifications of the dialogue at different points in the dialogue, wherein the storing the dialogue further includes storing the one or more classifications.
14. The computer program product of claim 12 , wherein the program instructions further cause the computing device to score user responses within the dialogues, wherein the updating is further based on the scoring the user responses.
15. The computer program product of claim 12 , wherein the program instructions further cause the computing device to: abridge text transcripts associated with the stored dialogue and the one more previously stored dialogues that are transitively related; and apply the updated question mapping to the subsequent support dialogue.
16. A system comprising: a CPU, a computer readable memory and a computer readable storage medium associated with a computing device; program instructions to store a plurality of dialogues between user devices and an automated support application hosted by the computing device; program instructions to determine transitive relationships between the plurality of dialogues; and program instructions to merge and abridge text transcripts of a subset of the plurality of dialogues that are transiently related to form an abridged text transcript; and program instructions to apply the abridged text transcript to a subsequent support dialogue, wherein the storing the plurality of dialogues comprises program instructions to store respective dialogue graphs associated with each of the plurality of dialogues, and the determining the transitive relationships comprises program instructions to match a subset of the plurality of dialogues based on respective dialogue graphs of each of the subset of the plurality of dialogues, and the program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory.
17. The system of claim 16 , wherein the storing the plurality of dialogues comprises program instructions to generate a dialogue graph of respective dialog graphs associated with the plurality of dialogues, wherein the generating the dialogue graph comprises program instructions to generate nodes representing user responses and responses by the automated support application and a path between the user responses and the responses by the automated support application.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
January 25, 2018
October 1, 2019
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.